20.500.12556/DKUM-50240 Automated landmark points detection by using a mixture of approaches the vole-teeth case This paper deals with the automated detection of a closed curvećs dominant points. We treat a curve as a 1-D function of the arc length. The problem of detecting dominant points is translated into seeking the extrema of the corresponding 1-D function. Three approaches for automated dominant points detection are presented: (1) an approach based on fitting polynomial, (2) an approach using 1-D computer registration and (3) an innovative approach based on a multi-resolution scheme, zero-crossing and hierarchical clustering. Afterwards, two methods are introduced based on the linearly and non-linearly mixing the results from the three approaches. We then mix the results in a mean-square error sense by using the linear and non-linear fittings, respectively. We experimentally demonstrate the problem of detecting 21 landmarks on 38 vole-teeth that by mixing, the detection accuracy is improved by up to 41.47 % with respect to the results for individual approaches, as applied within the mixture. closed curve dominant point landmark automated detection mixing model fitting vole-tooth true false false Angleški jezik Angleški jezik Delo ni kategorizirano 2015-07-10 12:37:28 2015-07-10 12:37:28 2022-05-29 03:06:25 2019-07-10 21:47:00 2015 0 0 str. 93-104 no. 1 Vol. 9 Jan. 2015 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.93 13373718 16578070 10.1007/s11760-012-0414-1 1863-1703 URN:SI:UM:DK:DRHRWZEL http://link.springer.com/article/10.1007/s11760-012-0414-1# 1 https://dk.um.si/Dokument.php?lang=slv&id=74798 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0